CN113935233A - Feed formula optimization method, system, computer and storage medium - Google Patents
Feed formula optimization method, system, computer and storage medium Download PDFInfo
- Publication number
- CN113935233A CN113935233A CN202111142614.XA CN202111142614A CN113935233A CN 113935233 A CN113935233 A CN 113935233A CN 202111142614 A CN202111142614 A CN 202111142614A CN 113935233 A CN113935233 A CN 113935233A
- Authority
- CN
- China
- Prior art keywords
- feed
- raw material
- feed formula
- optimization
- formula
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003860 storage Methods 0.000 title claims abstract description 8
- 239000002994 raw material Substances 0.000 claims abstract description 85
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 56
- 235000015097 nutrients Nutrition 0.000 claims abstract description 20
- 241001465754 Metazoa Species 0.000 claims abstract description 18
- 238000010845 search algorithm Methods 0.000 claims abstract description 17
- 238000009472 formulation Methods 0.000 claims description 20
- 239000000203 mixture Substances 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 18
- 235000021049 nutrient content Nutrition 0.000 claims description 13
- 235000016709 nutrition Nutrition 0.000 claims description 12
- 230000002068 genetic effect Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 239000004615 ingredient Substances 0.000 claims description 7
- 238000002922 simulated annealing Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000035764 nutrition Effects 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 235000019728 animal nutrition Nutrition 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 241000282898 Sus scrofa Species 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 241000282887 Suidae Species 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- VTYYLEPIZMXCLO-UHFFFAOYSA-L Calcium carbonate Chemical compound [Ca+2].[O-]C([O-])=O VTYYLEPIZMXCLO-UHFFFAOYSA-L 0.000 description 2
- KDXKERNSBIXSRK-UHFFFAOYSA-N Lysine Natural products NCCCCC(N)C(O)=O KDXKERNSBIXSRK-UHFFFAOYSA-N 0.000 description 2
- 239000004472 Lysine Substances 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 235000021048 nutrient requirements Nutrition 0.000 description 2
- 235000019629 palatability Nutrition 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 235000019750 Crude protein Nutrition 0.000 description 1
- FFEARJCKVFRZRR-BYPYZUCNSA-N L-methionine Chemical compound CSCC[C@H](N)C(O)=O FFEARJCKVFRZRR-BYPYZUCNSA-N 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 235000019779 Rapeseed Meal Nutrition 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011575 calcium Substances 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 229910000019 calcium carbonate Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000019864 coconut oil Nutrition 0.000 description 1
- 239000003240 coconut oil Substances 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 235000012343 cottonseed oil Nutrition 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- 235000003642 hunger Nutrition 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 229930182817 methionine Natural products 0.000 description 1
- 235000006286 nutrient intake Nutrition 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 239000003755 preservative agent Substances 0.000 description 1
- 239000004456 rapeseed meal Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 239000003440 toxic substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Animal Husbandry (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, a computer and a storage medium for optimizing a feed formula, wherein the method comprises the following steps: firstly, selecting feed formula raw materials according to actual conditions, obtaining the content of nutrient components of the selected raw materials by looking up feed components and a nutrient value table, and determining the nutrient demand of an animal according to the fed animal and a reference document. And then, establishing a feed formula optimization model, and solving the established feed formula optimization model. And finally, optimizing the result obtained by solving through an improved tabu search algorithm to finally obtain the optimal feed formula. On the basis of the result obtained by the traditional optimization algorithm or the intelligent optimization algorithm, the invention realizes the jumping-out local optimum global search by utilizing the improved tabu search algorithm to find out a better optimum solution, and the obtained feed formula can meet the restrictive constraint condition and reduce the cost to the maximum extent.
Description
Technical Field
The invention relates to the technical field of feed formula optimization, in particular to a feed formula optimization method, a feed formula optimization system, a computer and a storage medium.
Background
In the formula development of the feed, due to the diversity of the nutrient components of the raw materials and the complexity of the nutritional indexes required by animals, various constraint conditions can be met during the target solution. Cost reduction needs to be realized while the limiting conditions are met, and a plurality of problems such as time complexity, search range, result precision and the like need to be considered in the solving process, so that the difficulty is increased for the research of the feed formula. Because the traditional manual algorithm, linear programming method or local search method can not meet the realistic requirements, the formula covers more raw materials and the market price of the raw materials is continuously changed, and the quality of the required result is poor. Although the intelligent optimization algorithm has good performance, the result obtained by simply using the group intelligent optimization algorithm is good, but the restrictive constraint condition control cannot be well met in time complexity and precision control. Therefore, it is important to obtain a feed formula which can satisfy restrictive constraint conditions and reduce the cost to the maximum extent.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a feed formula optimization method, so that a feed formula which can meet restrictive constraint conditions and reduce the cost to the maximum extent is obtained.
In order to achieve the purpose, the technical scheme provided by the invention is as follows:
a feed formula optimization method comprises the following steps:
s1, selecting raw materials of the feed formula according to actual conditions;
s2, obtaining the nutrient content of the raw material selected in the step S1 by referring to the feed ingredients and the nutrient value table;
s3, determining the nutritional requirement of the animal according to the fed animal and the reference;
s4, establishing a feed formula optimization model;
s5, solving the feed formula optimization model established in the step S4;
s6, optimizing the result obtained by the step S5 through an improved tabu search algorithm, and finally obtaining the optimal feed formula.
Further, when selecting the feed formulation raw materials in combination with actual conditions in step S1, the consideration of the raw materials includes the type of raw materials, the volume of raw materials, the characteristics of raw materials, the mixing conditions of raw materials, and the unit price of raw materials; the unit price of the feedstock includes the value and shipping cost of the feedstock itself.
Further, the process of establishing the feed formula optimization model in step S4 is as follows:
with m raw materials and n feed nutritional requirements, a matrix P (a) of n x m is constructedij)，i＝1，2，...，n；j＝1，2，...，m；
Assuming that the feed cost is E, the objective function in the feed formulation optimization model is defined as follows:
minE＝c1x1+c2x2+...+cmxm (1)
in the formula (1), xi(i ═ 1., m) is the content of each raw material in the formula, x1+x2+...+xmEqual to the total weight of the feed formulation, c1，c2，...，cmUnit price per raw material;
for the relevant constraint conditions of the feed, the following inequality equations are used for describing:
in the formula (2), aijThe content of the jth nutrient component contained in the ith raw material; biIs the minimum standard of each nutrient component required by the fed animals.
Further, the step S5 is to solve the feed formula optimization model established in the step S4 through a traditional optimization algorithm or an intelligent optimization algorithm;
wherein, the traditional optimization algorithm adopts an exhaustion method or a linear programming method;
the intelligent optimization algorithm adopts a genetic algorithm, a particle swarm algorithm or a simulated annealing algorithm.
Further, the specific process of the step S6 for optimizing the result obtained by the step S5 through the improved tabu search algorithm is as follows:
s6-1, result X ═ X obtained in step S51，x2，...，xm]，xi(i ═ 1., m) is the content of each raw material in the formula, and the corresponding feed cost is f; set search precision matrix W ═ W1，w2，...，wp]The iteration number K, K is 0; defining a tabu table T comprising a neighborhood moving matrix;
s6-2, judging whether K is larger than K, if so, jumping to the step S6-8, otherwise, setting i to 1, and proceeding to the step S6-3;
s6-3, judging whether i is larger than p, if so, changing k to k +1, returning to the step S6-2, otherwise, entering the step S6-4;
s6-4, input precision wiCarry out neighborhood shift, for two different elements in X + w respectivelyiAnd-wiObtaining 2M (M-1) different neighborhood movement matrixes M;
s6-5, comparing all the neighborhood moving matrixes M obtained in the step S6-4 with the neighborhood moving matrixes in the tabu list T one by one, and if the sum of the current neighborhood moving matrix M and the neighborhood moving matrixes in the tabu list T is zero, rejecting a solution X corresponding to the current neighborhood moving matrix M;
s6-6, substituting the residual solution X obtained in the step S6-5 into constraint conditions, and removing unsatisfactory solution X;
s6-7, substituting the residual solutions X in the step S6-6 into an objective function, comparing the feed cost E corresponding to each residual solution X, solving the current optimal solution X, recording and updating the feed cost f, then updating the neighborhood moving matrix M corresponding to the optimal solution X into a tabu table T, wherein i is i +1, and returning to the step S6-3;
s6-8, outputting the final result X and the corresponding feed cost f.
In order to achieve the above object, the present invention further provides a feed formula optimization system for implementing the feed formula optimization method, which comprises a feed formula raw material selection module, a raw material nutrient content acquisition module, an animal nutrient demand determination module, a modeling module, a solving module and an optimization module, which are connected in sequence;
wherein the content of the first and second substances,
the feed formula raw material selection module is used for selecting feed formula raw materials by combining with actual conditions;
the raw material nutrient content acquisition module is used for acquiring the nutrient content of the raw material selected by the feed formula raw material selection module by looking up feed ingredients and a nutrient value table;
the animal nutrition demand determination module is used for determining the nutrition demand of the animal according to the fed animal and a reference;
the modeling module is used for establishing a feed formula optimization model;
the solving module is used for solving the feed formula optimization model established by the modeling module;
and the optimization module is used for optimizing the result obtained by solving by the solving module to finally obtain the optimal feed formula.
To achieve the above object, the present invention further provides a computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to realize the steps of the feed formulation optimization method.
To achieve the above object, the present invention further provides a storage medium storing a computer program, which when executed by a processor, implements the steps of the above feed formulation optimization method.
Compared with the prior art, the principle and the advantages of the technical scheme are as follows:
according to the technical scheme, the raw materials of the feed formula are selected according to actual conditions, the nutrient content of the selected raw materials is obtained by looking up feed components and a nutrient value table, and the nutrient requirement of an animal is determined according to the fed animal and a reference document. And then, establishing a feed formula optimization model, and solving the established feed formula optimization model. And finally, optimizing the result obtained by solving through an improved tabu search algorithm to finally obtain the optimal feed formula.
The technical scheme can obtain the feed formula which can meet restrictive constraint conditions and reduce the cost to the maximum extent. Specifically, in the process, the traditional optimization algorithm or the intelligent optimization algorithm is used for searching the initial point in combination with the actual situation, because high-precision searching is not needed, if an exhaustion method or a linear programming method is adopted, the running time is short, and then on the basis of the required result, the improved tabu search algorithm is used for realizing the jump-out local optimum global search to find a more optimum solution. And because the algorithm is only optimized aiming at the result and does not relate to the structural change of the algorithm, the algorithm can be nested with other algorithms to realize the re-optimization of the result, can realize the control on the precision of the optimized result by setting parameters, and can overcome the defect that the search process is easy to early converge so as to realize the global optimization and obtain better results.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the services required for the embodiments or the technical solutions in the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for optimizing a feed formulation according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of the optimization of the results obtained by the solution by the improved tabu search algorithm;
fig. 3 is a schematic structural diagram of a feed formula optimization system according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
As shown in fig. 1, this example describes a formulation optimization method for pig feed, comprising the following steps:
s1, selecting raw materials of the feed formula according to actual conditions;
in the process of preparing the feed, the selection of the raw materials is one of the important links, and the conditions to be considered comprise the types of the raw materials, the volumes of the raw materials, the characteristics of the raw materials, the mixing conditions of the raw materials and the unit prices of the raw materials; the unit price of the feedstock includes the value and shipping cost of the feedstock itself.
The specific principle is as follows:
1) the types of raw materials are as follows: the varieties of the raw materials are diversified, so that the nutrition complementation among various raw materials is favorably exerted;
2) volume of raw material: the volume of the selected raw materials is adapted to the volume of the pig digestive tract. If the volume is too large, the pigs are full under the condition of not using up the feed, and the situation of insufficient nutrient intake can occur; if the volume is too small, uneasiness and anxiety due to hunger will occur, which will affect the growth rate.
3) The characteristics of the raw materials are as follows: the palatability of the raw material, the content of toxic substances in the raw material, and whether the preservability is good or not need to be grasped in detail. The palatability is not good, or raw materials which need to be added with a large amount of preservatives are not suitable for selection due to poor storage property, and raw materials with strong pollution in the feed production process are not suitable for selection.
4) Mixing condition of raw materials: the raw materials must be mixed uniformly, and it should be understood that there are other chemical reactions that produce other substances that are not beneficial to the growth and development of pigs after mixing. Especially, when the premix is added, the livestock is easy to be poisoned due to uneven mixing, and the growth and development are influenced.
5) Unit price of raw material: the principle of local conditions and local materials should be adhered to during raw material selection, unnecessary transportation cost is avoided, cost is reduced, and local raw material resources are fully utilized.
The following raw materials of the feed formula are selected and obtained by combining the actual conditions: corn, rice bran meal, bean pulp, rapeseed meal, cottonseed meal, coconut oil, stone powder, calcium hydrophosphate and lysine.
S2, obtaining the nutrient content of the raw material selected in the step S1 by referring to the feed ingredient and nutrient value table, as shown in Table 1 below
TABLE 1
S3 determining nutrient requirement of fed pig according to the reference, as shown in Table 2
| Item | Standard of nutrition |
| Metabolic energy | 14.23 |
| Crude protein | 15.50 |
| Calcium carbonate | 0.50 |
| With phosphorus release | 0.19 |
| Lysine | 0.75 |
| Methionine | 0.20 |
TABLE 2
S4, establishing a feed formula optimization model;
with m raw materials and n feed nutritional requirements, a matrix P (a) of n x m is constructedij)，i＝1，2，...，n；j＝1，2，...，m；
Assuming that the feed cost is E, the objective function in the feed formulation optimization model is defined as follows:
minE＝c1x1+c2x2+...+cmxm (1)
in the formula (1), xi(i ═ 1., m) is the content of each raw material in the formula, x1+x2+...+xmEqual to the total weight of the feed formulation, c1，c2，...，cmUnit price per raw material;
for the relevant constraint conditions of the feed, the following inequality equations are used for describing:
in the formula (2), aijThe content of the jth nutrient component contained in the ith raw material; biIs the minimum standard of each nutrient component required by the pigs.
S5, solving the feed formula optimization model established in the step S4 through a traditional optimization algorithm or an intelligent optimization algorithm; the traditional optimization algorithm comprises an exhaustion method, a linear programming method and the like; the intelligent optimization algorithm comprises a genetic algorithm, a particle swarm algorithm, a simulated annealing algorithm and the like. Which method is employed depends on the particular circumstances.
Among the above, the accuracy of the exhaustive method and the linear programming method is not high, but the time used is short;
the genetic algorithm, the particle swarm algorithm and the simulated annealing algorithm have high precision, but the calculation time is too long, so that a large amount of time cost is consumed.
S6, optimizing the result obtained by the step S5 through an improved tabu search algorithm, and finally obtaining the optimal feed formula.
The essence of the tabu search algorithm is that global search and local search are realized through a tabu table. Firstly, setting algorithm parameters, generating an initial solution X, and setting a null tabu table; however, the initial solution of the traditional tabu search algorithm is randomly generated, so that the algorithm result is unstable and the optimization degree is low, so that the algorithm realizes calculation by using the traditional algorithm, and then the obtained result is used as the initial solution for optimization. And then judging whether a termination condition is met, generally setting the operation times or a threshold value reached by the result, outputting the result if the operation times or the threshold value is reached, and continuing the operation if the operation times or the threshold value is not reached. And then, moving the result X obtained in the previous step according to a neighborhood moving rule, and only changing the values of two variables in X at one time due to the requirement of keeping the proportion sum of the ingredients to be 100% in the problem. Because there are multiple variable values in X, under the condition that the neighborhood change values are the same, a round of neighborhood movement has new solutions X, all the obtained solutions are substituted into the limiting conditions, and whether the corresponding neighborhood movement rules are in the taboo table or not is judged, and rejection is not satisfied. Substituting all feasible solutions into the objective function, finding out the optimal solution, recording the adaptive value of the objective function, the optimal solution and the neighborhood movement corresponding to the optimal solution, putting the corresponding movement into a taboo table, and reusing the neighborhood movement until a specified algebra is reached (since the sum of variables in X is constant, the neighborhood movement is also an increase and decrease operation, the privilege criterion is not involved, and the details are not described here). And finally, updating the solved optimal solution, updating the corresponding target function adaptive value and the corresponding algebra, and turning to the step of judging the termination condition.
As shown in fig. 2, the specific steps of optimizing the result obtained by the solution are as follows:
s6-1, result X ═ X obtained in step S51，x2，...，xm]，xi(i ═ 1., m) is the content of each raw material in the formula, and the corresponding feed cost is f; set search precision matrix W ═ W1，w2，...，wp]The iteration number K, K is 0; defining a tabu table T comprising a neighborhood moving matrix;
s6-2, judging whether K is larger than K, if so, jumping to the step S6-8, otherwise, setting i to 1, and proceeding to the step S6-3;
s6-3, judging whether i is larger than p, if so, changing k to k +1, returning to the step S6-2, otherwise, entering the step S6-4;
s6-4, input precision wiCarry out neighborhood shift, for two different elements in X + w respectivelyiAnd-wiObtaining 2M (M-1) different neighborhood movement matrixes M;
s6-5, comparing all the neighborhood moving matrixes M obtained in the step S6-4 with the neighborhood moving matrixes in the tabu list T one by one, and if the sum of the current neighborhood moving matrix M and the neighborhood moving matrixes in the tabu list T is zero, rejecting a solution X corresponding to the current neighborhood moving matrix M (so that the situation that the optimal value searched in the previous step cannot jump out due to the fact that the previous step is excellent can be avoided);
s6-6, substituting the residual solution X obtained in the step S6-5 into constraint conditions, and removing unsatisfactory solution X;
s6-7, substituting the residual solutions X in the step S6-6 into an objective function, comparing the feed cost E corresponding to each residual solution X, solving the current optimal solution X, recording and updating the feed cost f, then updating the neighborhood moving matrix M corresponding to the optimal solution X into a tabu table T, wherein i is i +1, and returning to the step S6-3;
s6-8, outputting the final result X and the corresponding feed cost f.
In order to verify the effectiveness and superiority of the method described in this embodiment, the method (ITS), the linear programming algorithm (LP), the target programming algorithm (GP), the fuzzy linear programming algorithm (FLP), the random programming algorithm (SP), the simulated annealing search algorithm (SAA), the standard Genetic Algorithm (GA), and the Hybrid Genetic Algorithm (HGA) described in this embodiment are respectively adopted to optimize the feed formula of the pig, and the optimization results are shown in table 3 below:
cost comparison of tabu search algorithm with linear programming, goal programming, fuzzy linear programming, stochastic programming, simulated annealing search, standard genetic algorithm, and hybrid genetic algorithm in feed formulation
*LP is linear programming; GP is a target planning; FLLP is fuzzy linear programming; SP is random planning: SAA is simulated annealing search: the standard genetic algorithm is GA; hybrid genetic algorithm is HGA
TABLE 3
Through comparison, the variety of raw materials required by the results obtained by GP and FLP algorithms is more, and a great amount of manpower and material resources are consumed in the process of finding a suitable raw material manufacturer; the cost of the result obtained by the SP algorithm is up to 2075.44 yuan per ton, and the cost is too high; the LP algorithm is used as a linear programming algorithm, is not suitable for a non-linear nutrition equation, and has great limitation; the SAA, GA and HGA algorithms have the problems that the calculation time of the genetic algorithm is too long, a large amount of time cost is consumed, and the result may not have timeliness. In summary, the method described in this example has the best performance in reducing the overall cost of a swine feed formulation compared to other methods using different algorithms, with significant time, labor, and capital savings.
In addition to describing the feed formula optimization method, the present embodiment also describes a feed formula optimization system, which is used for implementing the feed formula optimization method and includes a feed formula raw material selection module 1, a raw material nutrient content acquisition module 2, an animal nutrient demand determination module 3, a modeling module 4, a solving module 5, and an optimization module 6, which are connected in sequence;
wherein the content of the first and second substances,
the feed formula raw material selection module 1 is used for selecting feed formula raw materials according to actual conditions;
the raw material nutrient content acquisition module 2 is used for acquiring the nutrient content of the raw material selected by the feed formula raw material selection module 1 by looking up feed ingredients and a nutrient value table;
the animal nutrition demand determination module 3 is used for determining the nutrition demand of the pig according to the pig combined reference;
the modeling module 4 is used for establishing a feed formula optimization model;
the solving module 5 is used for solving the feed formula optimization model established by the modeling module 4;
and the optimization module 6 is used for optimizing the result obtained by solving by the solving module 5 to finally obtain the optimal feed formula.
Further, the present embodiment also describes a computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the feed formulation optimization method.
Finally, the present embodiment also describes a storage medium storing a computer program which, when executed by a processor, performs the steps of the above-described feed formulation optimization method.
The above-mentioned embodiments are merely preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, so that variations based on the shape and principle of the present invention should be covered within the scope of the present invention.
Claims (8)
1. A feed formula optimization method is characterized by comprising the following steps:
s1, selecting raw materials of the feed formula according to actual conditions;
s2, obtaining the nutrient content of the raw material selected in the step S1 by referring to the feed ingredients and the nutrient value table;
s3, determining the nutritional requirement of the animal according to the fed animal and the reference;
s4, establishing a feed formula optimization model;
s5, solving the feed formula optimization model established in the step S4;
s6, optimizing the result obtained by the step S5 through an improved tabu search algorithm, and finally obtaining the optimal feed formula.
2. The method for optimizing a feedstuff formulation according to claim 1, wherein the conditions to be considered in selecting the feedstuff formulation in step S1 include the type of the raw material, the volume of the raw material, the characteristics of the raw material, the mixing condition of the raw material and the unit price of the raw material; the unit price of the feedstock includes the value and shipping cost of the feedstock itself.
3. The method for optimizing a feed formulation according to claim 1, wherein the step S4 comprises the following steps:
with m raw materials and n feed nutritional requirements, a matrix P (a) of n x m is constructedij)，i＝1，2，...，n；j＝1，2,...,m；
Assuming that the feed cost is E, the objective function in the feed formulation optimization model is defined as follows:
minE＝c1x1+c2x2+...+cmxm (1)
in the formula (1), xi(i ═ 1., m) is the content of each raw material in the formula, x1+x2+...+xmEqual to the total weight of the feed formulation, c1,c2,...,cmUnit price per raw material;
for the relevant constraint conditions of the feed, the following inequality equations are used for describing:
in the formula (2), aijThe content of the jth nutrient component contained in the ith raw material; biIs the minimum standard of each nutrient component required by the fed animals.
4. The feed formulation optimization method according to claim 3, wherein the step S5 is implemented by solving the feed formulation optimization model established in the step S4 through a traditional optimization algorithm or a smart optimization algorithm;
wherein, the traditional optimization algorithm adopts an exhaustion method or a linear programming method;
the intelligent optimization algorithm adopts a genetic algorithm, a particle swarm algorithm or a simulated annealing algorithm.
5. The method for optimizing a feed formula according to claim 4, wherein the step S6 is implemented by optimizing the result obtained by the step S5 through an improved tabu search algorithm as follows:
s6-1, result X ═ X obtained in step S51,x2,...,xm]，xi(i ═ 1., m) is the content of each raw material in the formula, and the corresponding feed cost is f; set search precision matrix W ═ W1,w2,...,wp]The iteration number K, K is 0; defining a tabu table T comprising a neighborhood moving matrix;
s6-2, judging whether K is larger than K, if so, jumping to the step S6-8, otherwise, setting i to 1, and proceeding to the step S6-3;
s6-3, judging whether i is larger than p, if so, changing k to k +1, returning to the step S6-2, otherwise, entering the step S6-4;
s6-4, input precision wiCarry out neighborhood shift, for two different elements in X + w respectivelyiAnd-wiObtaining 2M (M-1) different neighborhood movement matrixes M;
s6-5, comparing all the neighborhood moving matrixes M obtained in the step S6-4 with the neighborhood moving matrixes in the tabu list T one by one, and if the sum of the current neighborhood moving matrix M and the neighborhood moving matrixes in the tabu list T is zero, rejecting a solution X corresponding to the current neighborhood moving matrix M;
s6-6, substituting the residual solution X obtained in the step S6-5 into constraint conditions, and removing unsatisfactory solution X;
s6-7, substituting the residual solutions X in the step S6-6 into an objective function, comparing the feed cost E corresponding to each residual solution X, solving the current optimal solution X, recording and updating the feed cost f, then updating the neighborhood moving matrix M corresponding to the optimal solution X into a tabu table T, wherein i is i +1, and returning to the step S6-3;
s6-8, outputting the final result X and the corresponding feed cost f.
6. A feed formula optimization system for implementing the feed formula optimization method of any one of claims 1 to 5, characterized in that the feed formula optimization system comprises a feed formula raw material selection module (1), a raw material nutrient content acquisition module (2), an animal nutrient demand determination module (3), a modeling module (4), a solving module (5) and an optimization module (6) which are connected in sequence;
wherein the content of the first and second substances,
the feed formula raw material selection module (1) is used for selecting feed formula raw materials by combining with actual conditions;
the raw material nutrient content acquisition module (2) is used for acquiring the nutrient content of the raw material selected by the feed formula raw material selection module (1) by looking up feed ingredients and a nutrient value table;
the animal nutrition demand determination module (3) is used for determining the nutrition demand of the animal according to the fed animal and a reference;
the modeling module (4) is used for establishing a feed formula optimization model;
the solving module (5) is used for solving the feed formula optimization model established by the modeling module (4);
and the optimization module (6) is used for optimizing the result obtained by solving by the solving module (5) to finally obtain the optimal feed formula.
7. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any one of claims 1 to 5 are carried out when the program is executed by the processor.
8. A storage medium storing a computer program, characterized in that the program realizes the steps of the method of any one of claims 1-5 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111142614.XA CN113935233A (en) | 2021-09-28 | 2021-09-28 | Feed formula optimization method, system, computer and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111142614.XA CN113935233A (en) | 2021-09-28 | 2021-09-28 | Feed formula optimization method, system, computer and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113935233A true CN113935233A (en) | 2022-01-14 |
Family
ID=79277133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111142614.XA Pending CN113935233A (en) | 2021-09-28 | 2021-09-28 | Feed formula optimization method, system, computer and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113935233A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114947011A (en) * | 2022-05-26 | 2022-08-30 | 江苏邦鼎科技有限公司 | Method and system for improving puffing degree of low-starch feed |
| CN117121949A (en) * | 2023-09-22 | 2023-11-28 | 广州麦乐生物科技有限公司 | Adult formula milk powder for rebuilding and strengthening human immunity |
-
2021
- 2021-09-28 CN CN202111142614.XA patent/CN113935233A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114947011A (en) * | 2022-05-26 | 2022-08-30 | 江苏邦鼎科技有限公司 | Method and system for improving puffing degree of low-starch feed |
| CN114947011B (en) * | 2022-05-26 | 2024-03-08 | 江苏邦鼎科技有限公司 | Method and system for improving puffing degree of low-starch feed |
| CN117121949A (en) * | 2023-09-22 | 2023-11-28 | 广州麦乐生物科技有限公司 | Adult formula milk powder for rebuilding and strengthening human immunity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113935233A (en) | Feed formula optimization method, system, computer and storage medium | |
| Lassaletta et al. | Future global pig production systems according to the Shared Socioeconomic Pathways | |
| KR100879092B1 (en) | Computer system for determining a customized animal feed | |
| Krausmann et al. | Land-use change and socio-economic metabolism in Austria—Part I: driving forces of land-use change: 1950–1995 | |
| CN104054961A (en) | Growing and fattening pig feed containing cassavas and coconut meal and preparation method thereof | |
| CN112418607B (en) | Optimal selection method of multicomponent compound pellet feed formula | |
| Rahman et al. | Shrimp feed formulation via evolutionary algorithm with power heuristics for handling constraints | |
| CN113537639A (en) | Method and system for establishing fish growth prediction model as culture environment parameter | |
| CN110956380A (en) | Method for evaluating live pig breeding process based on improved analytic hierarchy process | |
| Sheppard | Elemental composition of swine manure from 1997 to 2017: changes relevant to environmental consequences | |
| CN110765603A (en) | Computer-based feed formula data optimization processing system and method | |
| Nasseri et al. | Animal diet formulation with floating price | |
| Zhang | Simulation of Chinese sorghum imports from a new perspective: US and global impacts | |
| Jeon | Mechanisms of labor transition during agricultural transformation: the cases of South Korea and Indonesia | |
| Samuel et al. | Tabu-genetic algorithm-based model for poultry feed formulation | |
| Haas | Home mix farming with food industry co-products: experience in the Netherlands and its worldwide possibilities. | |
| Fatyanosa et al. | Linear programming initialization method of evolution strategies for beef cattle feed optimization | |
| Žgajnar et al. | Multi-goal pig ration formulation; mathematical optimization approach | |
| CN107216173A (en) | A kind of preparation method of green fruit tree fertilizer | |
| CN115828734B (en) | Low-carbon feed formula method based on improved NSGA2 algorithm | |
| Pavlova et al. | Determining the optimal composition of feed mixtures in a cow farm using a mathematical model | |
| CN113408935B (en) | Breeding ecological analysis early warning method, device, medium and terminal equipment | |
| JAfarnejadi et al. | Evaluating the effect of iron and zinc micronutrient on wheat quantitative and qualitative yield under salinity stress in Khuzestan climate | |
| Proietti et al. | Environmental impact evaluation of dairy farms through life cycle assessment: a case study in Malta | |
| Singh | Modeling, Analysis, and Algorithmic Development of Some Scheduling and Logistics Problems Arising in Biomass Supply Chain, Hybrid Flow Shops, and Assembly Job Shops |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |